novel-downloader 1.4.5__py3-none-any.whl → 2.0.0__py3-none-any.whl

novel_downloader/core/searchers/ixdzs8.py

@@ -0,0 +1,107 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.searchers.ixdzs8
+--------------------------------------
+
+"""
+
+import logging
+
+from lxml import html
+
+from novel_downloader.core.searchers.base import BaseSearcher
+from novel_downloader.core.searchers.registry import register_searcher
+from novel_downloader.models import SearchResult
+
+logger = logging.getLogger(__name__)
+
+
+@register_searcher(
+    site_keys=["ixdzs8"],
+)
+class Ixdzs8Searcher(BaseSearcher):
+    site_name = "ixdzs8"
+    priority = 30
+    BASE_URL = "https://ixdzs8.com"
+    SEARCH_URL = "https://ixdzs8.com/bsearch"
+
+    @classmethod
+    async def _fetch_html(cls, keyword: str) -> str:
+        params = {"q": keyword}
+        try:
+            async with (await cls._http_get(cls.SEARCH_URL, params=params)) as resp:
+                return await cls._response_to_str(resp)
+        except Exception:
+            logger.error(
+                "Failed to fetch HTML for keyword '%s' from '%s'",
+                keyword,
+                cls.SEARCH_URL,
+            )
+            return ""
+
+    @classmethod
+    def _parse_html(cls, html_str: str, limit: int | None = None) -> list[SearchResult]:
+        doc = html.fromstring(html_str)
+        rows = doc.xpath("//ul[contains(@class,'u-list')]/li[contains(@class,'burl')]")
+        results: list[SearchResult] = []
+
+        for idx, row in enumerate(rows):
+            book_path = cls._first_str(row.xpath("./@data-url"))
+            if not book_path:
+                book_path = cls._first_str(
+                    row.xpath(".//h3[contains(@class,'bname')]/a/@href")
+                )
+            if not book_path:
+                continue
+
+            if limit is not None and idx >= limit:
+                break
+
+            book_id = book_path.strip("/").split("/")[-1]
+            book_url = cls._abs_url(book_path)
+
+            cover_rel = cls._first_str(
+                row.xpath(".//div[contains(@class,'l-img')]//img/@src")
+            )
+            cover_url = cls._abs_url(cover_rel) if cover_rel else ""
+
+            title = cls._first_str(
+                row.xpath(".//h3[contains(@class,'bname')]/a/@title")
+            ) or cls._first_str(row.xpath(".//h3[contains(@class,'bname')]/a/text()"))
+
+            author = cls._first_str(
+                row.xpath(".//span[contains(@class,'bauthor')]//a/text()")
+            )
+            word_count = cls._first_str(
+                row.xpath(".//span[contains(@class,'size')]/text()")
+            )
+
+            latest_chapter = cls._first_str(
+                row.xpath(
+                    ".//p[contains(@class,'l-last')]//span[contains(@class,'l-chapter')]/text()"
+                )
+            )
+            update_date = cls._first_str(
+                row.xpath(
+                    ".//p[contains(@class,'l-last')]//span[contains(@class,'l-time')]/text()"
+                )
+            )
+
+            # Compute priority
+            prio = cls.priority + idx
+
+            results.append(
+                SearchResult(
+                    site=cls.site_name,
+                    book_id=book_id,
+                    book_url=book_url,
+                    cover_url=cover_url,
+                    title=title,
+                    author=author,
+                    latest_chapter=latest_chapter,
+                    update_date=update_date,
+                    word_count=word_count,
+                    priority=prio,
+                )
+            )
+        return results

novel_downloader/core/searchers/jpxs123.py

@@ -0,0 +1,107 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.searchers.jpxs123
+---------------------------------------
+
+"""
+
+import logging
+
+from lxml import html
+
+from novel_downloader.core.searchers.base import BaseSearcher
+from novel_downloader.core.searchers.registry import register_searcher
+from novel_downloader.models import SearchResult
+
+logger = logging.getLogger(__name__)
+
+
+@register_searcher(
+    site_keys=["jpxs123"],
+)
+class Jpxs123Searcher(BaseSearcher):
+    site_name = "jpxs123"
+    priority = 30
+    BASE_URL = "https://www.jpxs123.com"
+    SEARCH_URL = "https://www.jpxs123.com/e/search/indexsearch.php"
+
+    @classmethod
+    async def _fetch_html(cls, keyword: str) -> str:
+        keyboard = cls._quote(keyword, encoding="gbk", errors="replace")
+        show = "title"
+        classid = "0"
+        body = f"keyboard={keyboard}&show={show}&classid={classid}"
+        headers = {
+            "Origin": "https://www.jpxs123.com",
+            "Referer": "https://www.jpxs123.com/",
+            "Content-Type": "application/x-www-form-urlencoded",
+        }
+        try:
+            async with (
+                await cls._http_post(cls.SEARCH_URL, data=body, headers=headers)
+            ) as resp:
+                return await cls._response_to_str(resp)
+        except Exception:
+            logger.error(
+                "Failed to fetch HTML for keyword '%s' from '%s'",
+                keyword,
+                cls.SEARCH_URL,
+            )
+            return ""
+
+    @classmethod
+    def _parse_html(cls, html_str: str, limit: int | None = None) -> list[SearchResult]:
+        doc = html.fromstring(html_str)
+        rows = doc.xpath('//div[@class="books m-cols"]/div[@class="bk"]')
+        results: list[SearchResult] = []
+
+        for idx, row in enumerate(rows):
+            href = cls._first_str(row.xpath(".//h3/a/@href"))
+            if not href:
+                continue
+
+            if limit is not None and idx >= limit:
+                break
+
+            book_id = href.strip("/").split(".", 1)[0].replace("/", "-")
+            book_url = cls._abs_url(href)
+
+            title = cls._first_str(row.xpath(".//h3/a//text()"))
+
+            cover_rel = cls._first_str(
+                row.xpath(".//div[contains(@class,'pic')]//a//img/@src")
+            )
+            cover_url = cls._abs_url(cover_rel) if cover_rel else ""
+
+            author = (
+                cls._first_str(
+                    row.xpath(".//div[contains(@class,'booknews')]/text()"),
+                    replaces=[("作者：", "")],
+                )
+                or "-"
+            )
+
+            update_date = cls._first_str(
+                row.xpath(
+                    ".//div[contains(@class,'booknews')]/label[contains(@class,'date')]/text()"
+                )
+            )
+
+            # Compute priority
+            prio = cls.priority + idx
+
+            results.append(
+                SearchResult(
+                    site=cls.site_name,
+                    book_id=book_id,
+                    book_url=book_url,
+                    cover_url=cover_url,
+                    title=title,
+                    author=author,
+                    latest_chapter="-",
+                    update_date=update_date,
+                    word_count="-",
+                    priority=prio,
+                )
+            )
+        return results

novel_downloader/core/searchers/piaotia.py

@@ -0,0 +1,100 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.searchers.piaotia
+---------------------------------------
+
+"""
+
+import logging
+
+from lxml import html
+
+from novel_downloader.core.searchers.base import BaseSearcher
+from novel_downloader.core.searchers.registry import register_searcher
+from novel_downloader.models import SearchResult
+
+logger = logging.getLogger(__name__)
+
+
+@register_searcher(
+    site_keys=["piaotia"],
+)
+class PiaotiaSearcher(BaseSearcher):
+    site_name = "piaotia"
+    priority = 30
+    SEARCH_URL = "https://www.piaotia.com/modules/article/search.php"
+
+    @classmethod
+    async def _fetch_html(cls, keyword: str) -> str:
+        # data = {
+        #     "searchtype": "articlename",
+        #     # "searchtype": "author",
+        #     # "searchtype": "keywords",
+        #     "searchkey": cls._quote(keyword, encoding="gbk", errors='replace'),
+        #     "Submit": cls._quote(" 搜 索 ", encoding="gbk", errors='replace'),
+        # }
+        searchtype = "articlename"
+        searchkey = cls._quote(keyword, encoding="gbk", errors="replace")
+        submit = cls._quote(" 搜 索 ", encoding="gbk", errors="replace")
+        body = f"searchtype={searchtype}&searchkey={searchkey}&Submit={submit}"
+        headers = {
+            "Origin": "https://www.piaotia.com",
+            "Referer": "https://www.piaotia.com",
+            "Content-Type": "application/x-www-form-urlencoded",
+        }
+        try:
+            async with (
+                await cls._http_post(cls.SEARCH_URL, data=body, headers=headers)
+            ) as resp:
+                return await cls._response_to_str(resp, encoding="gbk")
+        except Exception:
+            logger.error(
+                "Failed to fetch HTML for keyword '%s' from '%s'",
+                keyword,
+                cls.SEARCH_URL,
+            )
+            return ""
+
+    @classmethod
+    def _parse_html(cls, html_str: str, limit: int | None = None) -> list[SearchResult]:
+        doc = html.fromstring(html_str)
+        rows = doc.xpath('//table[@class="grid"]//tr[td]')
+        results: list[SearchResult] = []
+
+        for idx, row in enumerate(rows):
+            href = cls._first_str(row.xpath("./td[1]/a[1]/@href"))
+            if not href:
+                continue
+
+            if limit is not None and idx >= limit:
+                break
+
+            # "https://www.piaotia.com/bookinfo/14/14767.html" -> "14-14767"
+            book_id = href.rstrip(".html").split("bookinfo/")[-1].replace("/", "-")
+            book_url = cls._abs_url(href)
+
+            title = cls._first_str(row.xpath("./td[1]/a[1]//text()"))
+
+            latest_chapter = cls._first_str(row.xpath("./td[2]/a[1]//text()")) or "-"
+
+            author = cls._first_str(row.xpath("./td[3]//text()")) or "-"
+            word_count = cls._first_str(row.xpath("./td[4]//text()")) or "-"
+            update_date = cls._first_str(row.xpath("./td[5]//text()")) or "-"
+
+            # Compute priority incrementally
+            prio = cls.priority + idx
+            results.append(
+                SearchResult(
+                    site=cls.site_name,
+                    book_id=book_id,
+                    book_url=book_url,
+                    cover_url="",
+                    title=title,
+                    author=author,
+                    latest_chapter=latest_chapter,
+                    update_date=update_date,
+                    word_count=word_count,
+                    priority=prio,
+                )
+            )
+        return results

novel_downloader/core/searchers/qbtr.py

@@ -0,0 +1,106 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.searchers.qbtr
+------------------------------------
+
+"""
+
+import logging
+
+from lxml import html
+
+from novel_downloader.core.searchers.base import BaseSearcher
+from novel_downloader.core.searchers.registry import register_searcher
+from novel_downloader.models import SearchResult
+
+logger = logging.getLogger(__name__)
+
+
+@register_searcher(
+    site_keys=["qbtr"],
+)
+class QbtrSearcher(BaseSearcher):
+    site_name = "qbtr"
+    priority = 30
+    BASE_URL = "https://www.qbtr.cc"
+    SEARCH_URL = "https://www.qbtr.cc/e/search/index.php"
+
+    @classmethod
+    async def _fetch_html(cls, keyword: str) -> str:
+        keyboard = cls._quote(keyword, encoding="gbk", errors="replace")
+        show = "title"
+        classid = "0"
+        body = f"keyboard={keyboard}&show={show}&classid={classid}"
+        headers = {
+            "Origin": "https://www.qbtr.cc",
+            "Referer": "https://www.qbtr.cc/",
+            "Content-Type": "application/x-www-form-urlencoded",
+        }
+        try:
+            async with (
+                await cls._http_post(cls.SEARCH_URL, data=body, headers=headers)
+            ) as resp:
+                return await cls._response_to_str(resp)
+        except Exception:
+            logger.error(
+                "Failed to fetch HTML for keyword '%s' from '%s'",
+                keyword,
+                cls.SEARCH_URL,
+            )
+            return ""
+
+    @classmethod
+    def _parse_html(cls, html_str: str, limit: int | None = None) -> list[SearchResult]:
+        doc = html.fromstring(html_str)
+        rows = doc.xpath('//div[@class="books m-cols"]/div[@class="bk"]')
+        results: list[SearchResult] = []
+
+        for idx, row in enumerate(rows):
+            href = cls._first_str(row.xpath(".//h3/a[1]/@href"))
+            if not href:
+                continue
+
+            if limit is not None and idx >= limit:
+                break
+
+            # '/tongren/8850.html' -> "tongren-8850"
+            book_id = href.strip("/").split(".")[0].replace("/", "-")
+            book_url = cls._abs_url(href)
+
+            title = cls._first_str(row.xpath(".//h3/a[1]//text()"))
+
+            author = (
+                cls._first_str(
+                    row.xpath(".//div[contains(@class,'booknews')]/text()"),
+                    replaces=[("作者：", "")],
+                )
+                or "-"
+            )
+
+            update_date = (
+                cls._first_str(
+                    row.xpath(
+                        ".//div[contains(@class,'booknews')]/label[contains(@class,'date')]/text()"
+                    )
+                )
+                or "-"
+            )
+
+            # Compute priority
+            prio = cls.priority + idx
+
+            results.append(
+                SearchResult(
+                    site=cls.site_name,
+                    book_id=book_id,
+                    book_url=book_url,
+                    cover_url="",
+                    title=title,
+                    author=author,
+                    latest_chapter="-",
+                    update_date=update_date,
+                    word_count="-",
+                    priority=prio,
+                )
+            )
+        return results

novel_downloader/core/searchers/qianbi.py

@@ -0,0 +1,165 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.searchers.qianbi
+--------------------------------------
+
+"""
+
+import logging
+
+from lxml import html
+
+from novel_downloader.core.searchers.base import BaseSearcher
+from novel_downloader.core.searchers.registry import register_searcher
+from novel_downloader.models import SearchResult
+
+logger = logging.getLogger(__name__)
+
+
+@register_searcher(
+    site_keys=["qianbi"],
+)
+class QianbiSearcher(BaseSearcher):
+    site_name = "qianbi"
+    priority = 10
+    BASE_URL = "https://www.23qb.com/"
+    SEARCH_URL = "https://www.23qb.com/search.html"
+
+    @classmethod
+    async def _fetch_html(cls, keyword: str) -> str:
+        params = {"searchkey": keyword}
+        try:
+            async with (await cls._http_get(cls.SEARCH_URL, params=params)) as resp:
+                return await cls._response_to_str(resp)
+        except Exception:
+            logger.error(
+                "Failed to fetch HTML for keyword '%s' from '%s'",
+                keyword,
+                cls.SEARCH_URL,
+            )
+            return ""
+
+    @classmethod
+    def _parse_html(cls, html_str: str, limit: int | None = None) -> list[SearchResult]:
+        if html_str.find('<meta property="og:url"') != -1:
+            return cls._parse_detail_html(html_str)
+        return cls._parse_search_list_html(html_str, limit)
+
+    @classmethod
+    def _parse_detail_html(cls, html_str: str) -> list[SearchResult]:
+        """
+        Parse a single-book detail page, detected via <meta property="og:url">.
+
+        :param html_str: Raw HTML of the book detail page.
+        :return: A single-element list with the book's SearchResult.
+        """
+        doc = html.fromstring(html_str)
+
+        book_url = cls._first_str(doc.xpath("//meta[@property='og:url']/@content"))
+        if not book_url:
+            return []
+
+        # 'https://www.23qb.com/book/9268/' -> "9268"
+        book_id = book_url.split("book/", 1)[-1].strip("/")
+
+        cover_rel = cls._first_str(
+            doc.xpath("//div[contains(@class,'novel-cover')]//img/@data-src")
+        ) or cls._first_str(
+            doc.xpath("//div[contains(@class,'novel-cover')]//img/@src")
+        )
+        cover_url = cls._abs_url(cover_rel) if cover_rel else ""
+
+        title = cls._first_str(doc.xpath("//h1[@class='page-title']/text()"))
+        author = cls._first_str(doc.xpath("//a[contains(@href, '/author/')]/@title"))
+
+        latest_chapter = (
+            cls._first_str(
+                doc.xpath(
+                    "//div[@class='module-row-info']//a[@class='module-row-text']/@title"
+                )
+            )
+            or "-"
+        )
+        update_date = (
+            cls._first_str(
+                doc.xpath("//div[@class='module-heading newchapter']/time/text()"),
+                replaces=[("更新时间：", "")],
+            )
+            or "-"
+        )
+
+        word_count = cls._first_str(doc.xpath("//span[contains(text(), '字')]/text()"))
+
+        return [
+            SearchResult(
+                site=cls.site_name,
+                book_id=book_id,
+                book_url=book_url,
+                cover_url=cover_url,
+                title=title,
+                author=author,
+                latest_chapter=latest_chapter,
+                update_date=update_date,
+                word_count=word_count,
+                priority=cls.priority,
+            )
+        ]
+
+    @classmethod
+    def _parse_search_list_html(
+        cls, html_str: str, limit: int | None
+    ) -> list[SearchResult]:
+        """
+        Parse a multi-item search result page.
+
+        :param html_str: Raw HTML of the search-results page.
+        :param limit: Maximum number of items to return, or None for all.
+        :return: List of SearchResult.
+        """
+        doc = html.fromstring(html_str)
+        items = doc.xpath('//div[contains(@class,"module-search-item")]')
+        results: list[SearchResult] = []
+
+        for idx, item in enumerate(items):
+            href = cls._first_str(
+                item.xpath(".//div[@class='novel-info-header']/h3/a/@href")
+            )
+            if not href:
+                continue
+
+            if limit is not None and idx >= limit:
+                break
+
+            # '/book/9138/' -> "9138"
+            book_id = href.rstrip("/").split("/")[-1]
+            book_url = cls._abs_url(href)
+
+            title = cls._first_str(
+                item.xpath(".//div[@class='novel-info-header']/h3/a//text()")
+            )
+
+            cover_rel = cls._first_str(
+                item.xpath(".//div[contains(@class,'module-item-pic')]//img/@data-src")
+            ) or cls._first_str(
+                item.xpath(".//div[contains(@class,'module-item-pic')]//img/@src")
+            )
+            cover_url = cls._abs_url(cover_rel) if cover_rel else ""
+
+            # Compute priority
+            prio = cls.priority + idx
+
+            results.append(
+                SearchResult(
+                    site=cls.site_name,
+                    book_id=book_id,
+                    book_url=book_url,
+                    cover_url=cover_url,
+                    title=title,
+                    author="-",  # Author is not present on the page
+                    latest_chapter="-",
+                    update_date="-",
+                    word_count="-",
+                    priority=prio,
+                )
+            )
+        return results